Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
STATISTICAL PROCESS CONTROL TOOLS &
APPLICATIONS
Abstract Authors
The Statistical process control Swetha. S
methodology has been successfully used in Sri Ramachandra Faculty of Pharmacy
a variety of industrial and non-industrial SRIHER (DU)
domains. SPC charts are mostly utilised in Porur
manufacturing for process optimisation and Chennai, India.
control. It is a useful technique for solving
issues related to process consistency and Gayatri. S
capability enhancement by reducing Sri Ramachandra Faculty of Pharmacy
variability. SPC is a collection of tools used SRIHER (DU)
to monitor and assess the degree of quality Porur
of output produced by an organisation as Chennai, India.
well as to manage operations. The QC tools
were initially emphasised by Dr. Kaoru
Ishikawa. The initial set of seven QC tools
included a control charts, check sheet,
cause-and-effect diagram, Pareto chart,
histogram, stratification and scatter
diagram. This study provides an overview
of these QC tools that plays an important
role in obtaining, monitoring and analysing
data for identifying and resolving process
issues, which helps organisations attain
high quality performance.
Keywords: Statistical process control, QC
tools, Control chart, Check sheet, Fishbone
diagram, Histogram, Pareto chart,
Stratification, Scatter diagram
Copyright © 2024 Authors Page|224
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
I. INTRODUCTION
A statistical method of quality control known as statistical process control (SPC) is
used to monitor and manage a process so that it performs to its fullest ability. It establishes a
process's stability and predictability. It can be used in any process where it is possible to
measure whether the output of the product complies with specifications [1]. Statistical
process control is an effective problem-solving tool for achieving consistency in processes
and enhancing capability by lowering variability. It is the systematic use of statistical
methods to monitor and control the process to make sure that it runs as efficiently as possible
and produces a conforming product [2]. A key goal of statistical process control is to quickly
identify assignable causes of process shifts so that the process can be investigated and
corrective action can be taken before a large number of nonconforming units are produced
[3]. SPC is a methodology that has been widely applied in many kinds of industrial and non-
industrial fields. SPC charts are primarily used in manufacturing for process control and
improvement. The success or failure of an SPC operation is not determined by the size or
resources of the company, but rather by appropriate planning and immediate problem-solving
actions taken by employees [4]. SPC is a collection of tools used to manage operations as
well as assess and track the level of quality of an organization's outputs. SPC is necessary
because there is and always will be variation in the qualities of materials, products, services,
and people. The degree of variation in any purchased materials, services, processes, and
products can be measured, understood, and controlled using SPC techniques. If necessary,
this variation can be compared to previously established specifications.
Dr Kaoru Ishikawa, a professor of engineering at Tokyo University and the founder of
quality circles, originally emphasised the seven QC tools. He published a book in 1968
named Gemba no QC Shuho to educate Japanese workers on quality control methods and
procedures. It was intended to be used for "self-study and employee training" in QC reading
groups, or by foremen in the Japanese workplace. The seven fundamental quality control
tools were initially introduced in this book. The Asian Productivity Organisation released Dr.
Ishikawa's book, Guide to Quality Control, in English translation in 1971. Despite its
extensive usage, this book is still useful while using the seven fundamental tools. The initial
set of seven tools included a cause-and-effect diagram, a check sheet, control charts, a
histogram, a Pareto chart, a scatter diagram, and stratification. Some lists substitute a
flowchart or run chart for stratification. The seven quality control tools, the seven old tools,
or the seven basic tools are some of their alternate names [5,6].
II. BASIC QUALITY CONTROL TOOLS
1. Control Charts: Control charts are also known as Shewhart chart. A control chart is a
graphical method of monitoring a process and for generating a statistical based signal
when a process change takes place. It is one of the primary techniques of statistical
process control. In the control chart, a quality characteristic's average measurements in
process samples are plotted against time. The chart has an upper control limit (UCL), a
lower control limit (LCL) and a centre line (CL). The control limits are selected so that
almost all of the sample points will fall between them if the process is under control. The
centre line of the graph denotes the average value of the quality characteristic
corresponding to the in-control state.
Copyright © 2024 Authors Page|225
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Types of control chart: Control charts can be divided into two categories in general.
They are variable and attribute control chart.
Variable Chart: A quality characteristic is typically referred to as a variable if it can
be measured and expressed as a number on a continuous scale of measurement. It is
practical to describe the quality characteristic in such circumstances using a measure
of central tendency and a measure of variability. Variable control charts refer to
control charts for both central tendency and variability [2]. The chart is used to
increase process quality, determine capability of process, decide when to make
adjustments and when to leave the process alone, as well as to look into the root
causes of marginal or unacceptable quality. Additionally, it is used to decide on a
product's or service's specifications as well as the suitability of recently produced
goods or services [9]. Variable control charts are frequently used because they allow
for more effective control and give more details about how the processes are
performing.
The most popular ones are individual measurements control chart (x), mean
control chart (x bar), ranges control chart (R), and standard deviation control chart (s)
[7].
The process average or mean quality level is frequently controlled using the
control chart for mean, known as the X-bar Chart. To monitor process variability, a
control chart for the standard deviation, known as the S control chart, or a control
chart for the range, known as the R control chart, can be used [8].
Attribute Chart: Many quality attributes are not assessed on a continuous scale or
even a quantitative one. In these situations, we can determine whether each product
unit is conforming or nonconforming based on whether or not it possesses specific
characteristics, or we can count the number of nonconformities present on a product
unit. Attributes control charts are control charts for such quality characteristics [2].
Attributes charts are typically less informative than variables charts because a
numerical measurement contains more information than simply classifying a unit as
conforming or nonconforming. Attribute charts, on the other hand, have important
applications. They are especially helpful in-service industries and in non-
manufacturing quality improvement efforts because so many of the quality attributes
present in these settings are difficult to quantify on a numerical scale. The most
frequently used Attribute control chart are P chart, C chart and U chart [3].
The proportion of nonconforming or defective product produced by a
manufacturing process is represented by the control chart for fraction nonconforming,
also known as the P chart. The control chart for nonconformities, also known as a C
chart, is more practical because it focuses on the number of faults or nonconformities
observed rather than the proportion of nonconforming. The U chart, which measures
nonconformities per unit, is employed when the average number of nonconformities
per unit offers a more useful basis for process control [8].
Copyright © 2024 Authors Page|226
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Application of Control Chart: Use a control chart,
When monitoring ongoing operations, identifying and fixing issues as they arise.
When estimating the range of anticipated results from a process.
When assessing the stability of a process in statistical control.
When examining trends in process variation resulting from unique causes versus
common causes.
When deciding whether to focus your quality improvement effort on preventing
specific problems or making fundamental improvements to the process.
Figure 1: Control chart
2. Check Sheet: A systematic, prepared form for gathering and analysing data is a check
sheet. This is a versatile tool that may be used for many different tasks [6]. It is frequently
important to gather historical or real-time operational data regarding the process under
investigation in the early stages of process improvement [2]. Forms called check sheets
are employed to compile data in a methodical manner. They offer a "place to start" for the
user and a framework for gathering the data. Additionally, they help the user organise the
data for subsequent use. Creating histograms, Pareto charts, control charts, etc. can be
done using the information acquired on a check sheet. Check sheets have several
advantages, but their ease of use and comprehension and ability to create a clear image of
the situation are their main advantages.
Types of check sheet: The three major categories are defect-location check sheets,
tally check sheets, and defect-cause check sheets.
Defect-location check sheets: The sketch, drawing, or photo of the finished
product is typically included on the defect-location check sheet. The diagram is
labelled with the existence and type of issues or flaws [1]. This check sheet is also
known as concentration diagram, defect map, defect concentration check sheet,
location diagram [6].
Copyright © 2024 Authors Page|227
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Tally check sheets: The tally check sheet is used for measuring the instances of
various kinds of flaws. It is possible to lower the overall number of flaws by
taking the proper action by understanding the most common types of defects.
Defect-cause check sheets: The prior check sheets are used to identify specific
faults, such as their general location or root cause. A defect-cause check sheet is
utilised, though, when further details on a defect's cause are needed. To identify
the causes of low quality, a defect-cause check sheet was used [1].
Application of check sheets: Use check sheet,
When information may be repeatedly observed and gathered by the same
individual or at the same place.
When gathering information on the frequency or trends of incidents, faults, or
flaws, as well as their causes or locations.
When gathering information about a production process. [6]
3. Fishbone Diagram: The Fishbone diagram, also known as the Ishikawa diagram, is a
tool for determining the underlying factors that contribute to quality issues. It was given
this name in honour of Kaoru Ishikawa, a Japanese quality control statistician who
introduced this chart in the 1960s [10]. A tool for analysis that offers a systematic way to
look at effects and the reasons that lead to or influence those effects is the fishbone
diagram. The Fishbone diagram can be referred to as a cause-and-effect diagram due to its
objective [11]. A cause-and-effect diagram is used to show the various types of product
nonconformities and how they relate to one another. It is helpful in directing
management, production engineers, and operators' attention to quality issues. The level of
technological understanding of the process typically increases with the creation of a good
cause-and-effect diagram [2]. This cause analysis tool is one of the seven basic quality
tools. The fishbone diagram identifies a number of potential sources for an impact or
problem. A brainstorming session can be organised using it. Ideas are categorised
instantly into practical groups [6]. Some advantages of creating a Fishbone diagram
include encouraging group participation and utilising group knowledge of the process,
identifying areas where data should be collected for further research, and helping to
identify the underlying causes of a problem or quality characteristic using a structured
approach [12]. The diagram's layout closely resembles the skeleton of a fish. The
representation can be made plain by using bevel line segments that slant towards a
horizontal axis to suggest the distribution of the various causes and sub-causes that give
rise to them. However, it can also be enhanced with qualitative and quantitative
evaluations, names and coding for the risks that characterise the causes and sub-causes,
elements that demonstrate their succession, as well as other distinct approaches to risk
management. The diagram can also be used to assess the risks of the effect's causes and
sub-causes, as well as its overall risk [13].
Types of fishbone diagram: The major types include cause enumeration diagram,
CEDAC (cause-and-effect diagram with the addition of cards), desired-result
fishbone, process fishbone, time-delay fishbone, reverse fishbone diagram.
Copyright © 2024 Authors Page|228
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Application of fishbone diagram
Finding potential sources of a problem.
When a team's thinking has a tendency to get stagnant [6].
Figure 2: Cause and effect diagram [16]
4. Pareto Chart: Pareto chart is also known as Pareto analysis or Pareto diagram. Pareto
analysis is a statistical decision-making technique used to select a small number of tasks
that have a significant overall impact. It is one of the most popular easy-to-use methods.
When attempting to determine which actions or elements within an organisation will have
the greatest impact, the Pareto analysis methodology is used. It lists the
information/factors in decreasing order of frequency of occurrence, starting with the
highest frequency and ending with the lowest frequency. A Pareto cart is frequently used
to illustrate the findings of a Pareto analysis. The chart shows the different factors being
taken into account in ranked order. 100 percent is calculated as the sum of all frequencies.
The "80-20 rule," which was developed by Italian economist Vilfredo Pareto, states that
the "useful many" occupy only the remaining 20% of cumulative occurrences while the
"vital few" occupy a significant portion (80%) [14]. Bar graphs are used in Pareto charts.
The bars are ordered with the longest on the left and the shortest to the right. The lengths
of the bars signify frequency or cost respectively. The chart effectively illustrates which
circumstances are more important in this way [6]. Pareto charts have numerous
applications. They not only offer a way to study and enhance quality, but also a way to
study and enhance efficiency, material waste, energy conservation, safety concerns, cost
savings, etc. A Pareto chart can be useful in almost any area that a team wants to research
[1]. Due to its ability to organise and inspire ideas, Pareto analysis is a creative technique
to examine the root causes of issues. However, it may be constrained by its rejection of
potentially significant problems that may be minor at first but will worsen with time. It
Copyright © 2024 Authors Page|229
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
should be used in conjunction with other analytical methods, such as fault tree analysis
and failure mode and consequences analysis, for instance [15].
Application of Pareto Chart: Use a pareto chart,
When examining information concerning the prevalence of issues or their root
causes in a process.
When there are numerous issues or reasons and you want to concentrate on the
biggest.
When examining broad causes through analysing their particular elements.
When discussing your data with others [6].
Figure 3: Pareto chart
5. Histogram: The term "histogram" refers to a visual representation of the frequency
distribution of observed values of a variable. It is a type of bar chart that aids users in
displaying the distribution of data and the degree of variation within a process while also
visualizing attribute and variable data of a product or process [17]. The variability of a
product or process is visually represented by the histogram, a type of bar chart. It displays
the mean, mode, and average central tendency measures. By placing the specifications on
the histogram, it is possible to demonstrate whether the product specifications are being
met. A histogram can also be used to examine and identify the variable's underlying
distribution [1].
Application of Histogram: Use a histogram,
When the data are numerical.
When establishing if the output of a process is roughly normally distributed, in
particular, you want to be able to see how the data are dispersed.
Determining whether a method can satisfy the needs of the customer.
Examining the appearance of the product of a supplier's procedure.
Copyright © 2024 Authors Page|230
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Determining if a process has changed from one period to another.
Identifying whether the results of two or more processes vary.
You want to let others know about the rapid and simple sharing of data.
Figure 4: Histogram
6. Startification: Stratification is a strategy used in conjunction with other data analysis
tools. The significance of the data can be obscured when it has been combined with data
from several sources or categories. The data is divided using this method, allowing
patterns to be seen. One of the first seven QC tools was stratification.
Application of Starification
Used Prior to gathering data.
When information is derived from multiple sources or circumstances, such as
shifts, days of the week, suppliers, or population groups it is used.
Used when isolating many sources or circumstances may be necessary for data
analysis [6].
Copyright © 2024 Authors Page|231
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Figure 5: Stratification
7. Scatter Diagram: A scatter diagram, which compares two variables, is a graph of point
plots. The distribution of the points reveals the existence or absence of a cause-and-effect
connection between two variables. Pairs of data for the two variables under investigation
must be provided in order to use a scatter diagram. In order to clearly show the existence
or absence of a cause-and-effect link and provide insight into the strength of that
relationship, scatter diagrams are particularly helpful. A scatter plot does not
automatically suggest that the observed association is statistically significant. For
statistical correlation, further investigation is needed in the form of probability charting or
the determination of the correlation coefficient. Additionally, it should be remembered
that the interpretation of a scatter diagram is limited to the range of values that were really
observed. Scatter diagram is also called scatter plot, X-Y graph [1].
Application of scatter diagram: Use scatter diagram,
In the case of paired numerical data.
When each value of your independent variable's dependent variable could have
numerous values.
Consider when attempting to establish a connection between the two variables.
When attempting to pinpoint probable issues' underlying sources.
After listing potential causes and effects, utilise a fishbone diagram to verify
whether a specific cause and effect are actually connected.
When establishing whether two seemingly similar phenomena have the same
cause.
Before creating a control chart, check for autocorrelation [6].
Copyright © 2024 Authors Page|232
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
Figure 6: Scatter diagram
III. CONCLUSION
Statistical quality control is primarily concerned with ensuring that various procedures
and functional arrangements are in place to provide for successful and effective statistical
processes to minimise the probability of errors or issues in procedures or systems or in source
material. Quality control tools are simple to use and comprehend. They are primarily helpful
for resolving issues with quality control. It also aids in the ongoing improvement of
manufacturing process. By using these tools product rejection and product rework is reduced.
REFERENCES
[1] Omachonu, V.K., & Ross, J.E. (2004). Principles of Total Quality (3rd ed.). CRC Press.
[Link]
[2] Montgomery DC, Wiley J. Introduction to Statistical Quality Control. 7th Edition. New York: John Wiley
& Sons; 2009
[3] Montgomery DC, Wiley J. Introduction to Statistical Quality Control. Sixth Edition. New York: John
Wiley & Sons; 2009
[4] S. Subbulakshmi, A. Kachimohideen et al. An Essential Role of Statistical Process Control in Industries.
International Journal of Statistics and Systems. 12, (2), 2017, 355-362.
[5] Oakland, J.S. (2002). Statistical Process Control (5th ed.). Routledge.
[Link]
[6] Tague N. R. (2005). The quality toolbox (2nd ed.). ASQ Quality Press.
[7] Sengoz, [Link]. (2018). Control Charts to Enhance Quality. 10.5772/intechopen.73237.
[8] Naiknaware Tushar, Gaikwad Sakshi et al. Using measurement system analysis and statistical process
control for monitoring and reducing variation in the process. International Journal of Current Research. 14,
(10);22485-22488.
[9] Besterfield DH. Total Quality Management. 3rd ed. Upper Saddle River N.J: Prentice Hall; 2003.
[10] Juran, J. M. (1999). Juran's Quality Handbook (5th Edition). McGraw-Hill.
[11] Watson, G. (2004). The Legacy of Ishikawa. Quality Progress 37(4); 54-47.
[12] Basic Tools for Process Improvement. (1995, May 3). Retrived December 20, 2009, from Balanced
Scorecard Institute: [Link]
[13] Ciocoiu, C. N. (2008). Managementul riscului. Teorii, practici, metodologii. Bucharest: ASE.
[14] Talib, Faisal & Rahman, Zillur & Qureshi, Mohamed Rafik. (2010). Pareto analysis of total quality
management factors critical to success for service industries. International Journal for Quality Research. 4;
155-168.
[15] [Link]
Copyright © 2024 Authors Page|233
Futuristic Trends in Pharmacy & Nursing
e-ISBN: 978-93-6252-900-8
IIP Series, Volume 3, Book 19, Part 2, Chapter 7
STATISTICAL PROCESS CONTROL TOOLS & APPLICATIONS
[16] Fishbone tool of investigation in pharmaceuticals - Pharmaguideline.
[17] Neyestani, Behnam. (2017). Seven Basic Tools of Quality Control: The Appropriate Techniques for
Solving Quality Problems in the Organizations. 10.5281/zenodo.400832.
Copyright © 2024 Authors Page|234